INDEX

Explanations

instances of the word "and" and its variants, indicating a focus on conjunctions and connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oran

-0.15

igm

-0.15

undo

-0.14

æĭį

-0.14

agnost

-0.14

icho

-0.14

 ÑģÑĤÐ°Ð²

-0.14

urf

-0.13

Ã¢n

-0.13

dda

-0.13

POSITIVE LOGITS

aleb

0.16

Fcn

0.15

nbsp

0.15

 Duncan

0.14

hee

0.14

iov

0.14

arden

0.14

ãĥ³ãĤ¸

0.14

elden

0.14

.NULL

0.14

Activations Density 0.437%

instances of the word "and" and its variants, indicating a focus on conjunctions and connections between ideas

No Comments

No Known Activations