INDEX

Explanations

specific identifiers or codes associated with entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orough

-0.16

HLT

-0.16

EVT

-0.15

jerne

-0.14

lp

-0.14

akeup

-0.14

ensch

-0.14

urn

-0.14

aper

-0.13

Nullable

-0.13

POSITIVE LOGITS

eron

0.15

horn

0.14

eti

0.14

 ç¯

0.13

 bounded

0.13

uck

0.13

ç¿°

0.13

çķª

0.12

æ¸Ī

0.12

chio

0.12

Activations Density 1.975%

specific identifiers or codes associated with entities or organizations

No Comments

No Known Activations