INDEX

Explanations

words related to promoting positive actions or behaviors

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

erna

-0.16

Uploaded

-0.15

igger

-0.15

bern

-0.14

ominated

-0.14

 dest

-0.14

omo

-0.14

igm

-0.14

ouse

-0.13

irl

-0.13

POSITIVE LOGITS

/prom

0.19

EIF

0.15

QRST

0.15

 IMPLIED

0.14

stuff

0.14

à¤¾à¤¨à¤®

0.14

Ã¡la

0.14

ãĥªãĥ³ãĤ°

0.14

ials

0.14

iddi

0.14

Activations Density 0.019%

words related to promoting positive actions or behaviors

No Comments

No Known Activations