INDEX

Explanations

terms related to historical context or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 latter

-0.17

 ifndef

-0.15

Ð±ÑĥÐ´ÑĮ

-0.15

ESH

-0.14

åıİ

-0.14

Ð¾ÑĤÐµ

-0.14

 OTHERWISE

-0.14

gnore

-0.13

Ä°S

-0.13

izo

-0.13

POSITIVE LOGITS

etooth

0.16

See

0.15

see

0.14

See

0.14

èĪ¬

0.13

edula

0.13

esan

0.13

ofil

0.13

nnen

0.13

Activations Density 0.020%

terms related to historical context or significance

No Comments

No Known Activations