INDEX

Explanations

references to specific categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

uzzi

-0.16

olk

-0.16

elt

-0.15

/hash

-0.14

 pstmt

-0.14

urr

-0.14

enga

-0.14

jen

-0.14

enger

-0.14

èķ

-0.14

POSITIVE LOGITS

 sources

0.18

/source

0.17

 source

0.17

/sources

0.16

SOURCE

0.16

ophil

0.14

atego

0.14

=https

0.14

:http

0.14

¶

0.14

Activations Density 0.004%

references to specific categories or classifications

No Comments

No Known Activations