INDEX

Explanations

the occurrence of the word "some" in various contexts, indicating a focus on indefinite quantity or non-specificity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lÃŃ

-0.17

edly

-0.16

uÃ§

-0.15

 tavs

-0.15

lobe

-0.15

ilot

-0.14

kud

-0.14

*)((

-0.14

åĿĬ

-0.14

stva

-0.14

POSITIVE LOGITS

arda

0.17

rolls

0.16

adia

0.15

Î¯Î¿ÏĤ

0.14

rive

0.14

ymm

0.14

hur

0.14

croll

0.14

 ausp

0.14

odie

0.14

Activations Density 0.021%

the occurrence of the word "some" in various contexts, indicating a focus on indefinite quantity or non-specificity

No Comments

No Known Activations