INDEX

Explanations

terms related to governmental and systematic structures

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

oling

-0.15

-0.14

ingham

-0.14

patrick

-0.14

åľ

-0.14

Dump

-0.14

 flexGrow

-0.14

ÅĤaw

-0.14

çķª

-0.13

 Edgar

-0.13

POSITIVE LOGITS

iyan

0.17

/loose

0.17

 opposite

0.16

asers

0.16

ospel

0.16

odash

0.15

è·¯

0.14

cka

0.14

 leisure

0.14

ÏĥÎº

0.14

Activations Density 0.039%

terms related to governmental and systematic structures

No Comments

No Known Activations