INDEX

Explanations

references and mentions of "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

naz

-0.14

ilege

-0.14

ucket

-0.14

è°±

-0.14

è¶

-0.14

mia

-0.14

ANCEL

-0.13

èŃľ

-0.13

ãĥĭãĥ¼

-0.13

ÄĽn

-0.13

POSITIVE LOGITS

ONGL

0.16

oen

0.15

akens

0.15

/of

0.15

ãĤ·ãĥ§

0.15

0.14

ofil

0.14

æı¡

0.14

Activations Density 0.128%

references and mentions of "the."

No Comments

No Known Activations