INDEX

Explanations

formatting elements commonly found in code or structured documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

zte

-0.16

awy

-0.15

ÙģØ§Øª

-0.15

orry

-0.15

_ASSUME

-0.14

é¨

-0.14

ippo

-0.14

ffen

-0.14

awner

-0.14

inne

-0.14

POSITIVE LOGITS

Her

0.14

omanip

0.13

Zot

0.13

/rules

0.13

hi

0.13

 Fraser

0.13

Zam

0.13

isiÃ³n

0.13

 dare

0.13

Tro

0.13

Activations Density 0.000%

formatting elements commonly found in code or structured documents

No Comments

No Known Activations