INDEX

Explanations

instances of the article "a" and its variations, indicating a focus on nouns or varying quantities and specificity in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ungle

-0.14

olland

-0.13

enge

-0.13

 sorts

-0.13

 Ð³ÑĢÐ½

-0.13

VERTISE

-0.13

 Pets

-0.13

addin

-0.13

gere

-0.13

ê³

-0.13

POSITIVE LOGITS

 given

0.27

given

0.21

 particular

0.20

 Given

0.18

 GIVEN

0.17

_given

0.16

Given

0.16

ONSE

0.15

 individual

0.14

heim

0.14

Activations Density 0.248%

instances of the article "a" and its variations, indicating a focus on nouns or varying quantities and specificity in descriptions

No Comments

No Known Activations