INDEX

Explanations

terms related to political or societal groups and their dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

.decorate

-0.17

erus

-0.16

 Ð·Ð°Ñģ

-0.15

 Klopp

-0.14

gnore

-0.14

au

-0.14

>",

-0.14

iked

-0.14

 Friedrich

-0.14

aepernick

-0.14

POSITIVE LOGITS

isko

0.17

ettel

0.15

nda

0.15

ges

0.15

iral

0.15

/misc

0.14

zig

0.14

ploy

0.14

.RemoveAll

0.14

enga

0.14

Activations Density 0.010%

terms related to political or societal groups and their dynamics

No Comments

No Known Activations