INDEX

Explanations

phrases related to semantics and political discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

alla

-0.15

chalk

-0.14

ilar

-0.13

ifton

-0.13

lik

-0.13

ione

-0.13

 prior

-0.13

 diam

-0.13

rances

-0.13

POSITIVE LOGITS

 Hell

0.19

roulette

0.18

 hell

0.18

kab

0.16

 equivalent

0.16

 Gord

0.16

 Equivalent

0.16

Kab

0.15

 baise

0.15

etine

0.15

Activations Density 0.260%

phrases related to semantics and political discourse

No Comments

No Known Activations