INDEX

Explanations

conjunctions and linking words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

usercontent

-0.20

enda

-0.18

brane

-0.17

berman

-0.16

ãĥ

-0.15

mer

-0.15

ube

-0.15

-0.14

ographs

-0.14

åĮ

-0.14

POSITIVE LOGITS

acon

0.16

nbsp

0.16

à¤²à¤Ĺ

0.15

_CONV

0.15

Ú¾

0.14

agini

0.14

_DIRS

0.14

à¸£à¸§à¸¡

0.14

reas

0.14

LAY

0.14

Activations Density 0.041%

conjunctions and linking words

No Comments

No Known Activations