INDEX

Explanations

words related to responses and resolutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

sworth

-0.18

ton

-0.18

orton

-0.17

tons

-0.16

teness

-0.15

OURCE

-0.15

tega

-0.15

illion

-0.15

olver

-0.15

ensity

-0.15

POSITIVE LOGITS

=res

0.19

-res

0.19

/res

0.17

ibo

0.17

.Res

0.17

.locals

0.17

Res

0.17

(res

0.16

[res

0.16

idual

0.15

Activations Density 0.119%

words related to responses and resolutions

No Comments

No Known Activations