INDEX

Explanations

statements that express assumptions or inferences based on evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 principalTable

-0.12

ichtet

-0.12

warts

-0.12

ÏĦÎ¿Î¹

-0.12

alach

-0.12

åĵŃ

-0.11

 EXEMPLARY

-0.11

 nháº¯c

-0.11

ancell

-0.11

objs

-0.11

POSITIVE LOGITS

 conject

0.46

 guesses

0.45

 speculation

0.45

 guessing

0.45

 guess

0.43

çĮľ

0.43

 guessed

0.42

ded

0.42

 assumption

0.42

 speculate

0.42

Activations Density 0.688%

statements that express assumptions or inferences based on evidence

No Comments

No Known Activations