INDEX

Explanations

concepts related to neutrality and impartiality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

olla

-0.16

asan

-0.15

akit

-0.14

die

-0.14

Solid

-0.14

alÄ±

-0.14

'{$

-0.13

IMS

-0.13

 beden

-0.13

 uÅ¾

-0.13

POSITIVE LOGITS

isplay

0.16

hend

0.16

egl

0.15

 source

0.15

Poz

0.14

asel

0.14

Bindable

0.14

 referee

0.14

<source

0.14

 neutrality

0.14

Activations Density 0.031%

concepts related to neutrality and impartiality in various contexts

No Comments

No Known Activations