INDEX

Explanations

contextual phrases that suggest conditional scenarios or situations

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

ernel

-0.20

indre

-0.18

jac

-0.17

iyi

-0.15

bih

-0.15

ortex

-0.15

minent

-0.14

IGO

-0.14

IGHL

-0.14

Signing

-0.14

POSITIVE LOGITS

ful

0.18

ziej

0.15

you

0.14

fl

0.14

usive

0.14

ouri

0.14

ional

0.14

Doe

0.14

ato

0.14

eva

0.13

Activations Density 0.011%

contextual phrases that suggest conditional scenarios or situations

No Comments

No Known Activations