INDEX

Explanations

mentions of Kamala Harris

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ti

-0.16

-handed

-0.16

ed

-0.16

ts

-0.16

-0.15

ardo

-0.15

tn

-0.15

il

-0.15

tl

-0.15

POSITIVE LOGITS

engin

0.18

ullo

0.16

ased

0.15

radi

0.15

htable

0.15

elijke

0.15

BYTES

0.14

 addslashes

0.14

Ã´m

0.14

ControlEvents

0.14

Activations Density 0.004%

mentions of Kamala Harris

No Comments

No Known Activations