INDEX

Explanations

instances of specific letters, particularly 'l', 'd', 'm', 'p', 's', and 'b', likely indicating a focus on certain phonetic patterns or letters in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orem

-0.20

ighton

-0.16

ninger

-0.15

rav

-0.15

-0.14

ilated

-0.14

rsp

-0.14

rava

-0.14

byterian

-0.14

POSITIVE LOGITS

ÑĢÐ¸ÑĤÐ¸

0.15

 lean

0.15

iven

0.15

Amt

0.14

atego

0.14

lease

0.14

RNA

0.13

.deepEqual

0.13

ECH

0.13

Activations Density 0.207%

instances of specific letters, particularly 'l', 'd', 'm', 'p', 's', and 'b', likely indicating a focus on certain phonetic patterns or letters in the text

No Comments

No Known Activations