INDEX

Explanations

notes or annotations within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

omain

-0.16

uki

-0.16

orum

-0.15

 epic

-0.15

ength

-0.15

odel

-0.14

udit

-0.14

 borderline

-0.14

Pek

-0.14

akh

-0.14

POSITIVE LOGITS

infeld

0.16

tin

0.15

ekim

0.14

lund

0.14

edException

0.14

ulen

0.14

_UNS

0.14

elerik

0.13

Ã²a

0.13

cej

0.13

Activations Density 0.013%

notes or annotations within a text

No Comments

No Known Activations