INDEX

Explanations

instances of the word "of" in various contexts

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

ifty

-0.17

ãĤ«ãĥ«

-0.16

rosso

-0.16

å¯¼

-0.16

SION

-0.15

 dust

-0.15

juan

-0.15

 ãĥ´

-0.14

yg

-0.14

ãĤ«ãĥ¼

-0.14

POSITIVE LOGITS

 kennen

0.14

ì¦Ŀ

0.13

typeName

0.13

aires

0.13

FTA

0.13

isco

0.13

atatype

0.13

shima

0.13

tape

0.13

\Eloquent

0.13

Activations Density 0.018%

instances of the word "of" in various contexts

No Comments

No Known Activations