INDEX

Explanations

references to government officials and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

/get

-0.14

.commands

-0.14

/Branch

-0.14

 apprec

-0.14

ighth

-0.13

à¹Ĥà¸ķ

-0.13

è¯ī

-0.13

á¿ĸ

-0.13

artic

-0.13

("%

-0.13

POSITIVE LOGITS

say

0.22

who

0.20

Say

0.18

/operators

0.18

say

0.18

 familiar

0.17

 believe

0.17

’

0.17

 estimate

0.17

who

0.17

Activations Density 0.070%

references to government officials and their actions

No Comments

No Known Activations