INDEX

Explanations

terms related to negative attributes or qualities, particularly regarding social or political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

_Tis

-0.18

_icall

-0.17

OffsetTable

-0.16

SupportedContent

-0.16

_vlog

-0.15

aliz

-0.15

_Lean

-0.15

$MESS

-0.15

ideographic

-0.15

 forControlEvents

-0.15

POSITIVE LOGITS

0.33

-in

0.21

-b

0.20

-d

0.20

-c

0.19

-s

0.19

-p

0.19

-out

0.19

-à¤¸

0.18

-v

0.18

Activations Density 0.787%

terms related to negative attributes or qualities, particularly regarding social or political issues

No Comments

No Known Activations