INDEX

Explanations

complex or multi-syllabic words that describe events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

itler

-0.16

pars

-0.15

ÙĦÙħØ§ÙĨ

-0.14

Æ°Æ¡ng

-0.14

atoon

-0.14

elerinden

-0.14

ÑįÑĤÐ¾Ð¼Ñĥ

-0.14

ÏĥÏĥÎ±

-0.14

alth

-0.13

atoi

-0.13

POSITIVE LOGITS

/mod

0.17

ÐµÑģÑı

0.17

ele

0.17

oten

0.17

ÑģÑı

0.16

se

0.16

ies

0.15

Ð¾ÑģÑĮ

0.15

ollen

0.15

me

0.14

Activations Density 0.066%

complex or multi-syllabic words that describe events or actions

No Comments

No Known Activations