INDEX

Explanations

instances of the word "left" and related directional terms

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

risk

-0.17

llib

-0.17

uw

-0.15

-hide

-0.14

appa

-0.14

rh

-0.14

ibar

-0.14

qualified

-0.14

hop

-0.14

ewire

-0.13

POSITIVE LOGITS

most

0.19

-hand

0.18

ness

0.17

tings

0.16

/right

0.16

bies

0.16

-leaning

0.16

sy

0.15

-wing

0.15

ISTS

0.15

Activations Density 0.041%

instances of the word "left" and related directional terms

No Comments

No Known Activations