INDEX

Explanations

instances of characters or representations in various narratives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

are

-0.16

 sorts

-0.15

endo

-0.15

opal

-0.15

et

-0.15

/out

-0.14

isle

-0.14

eye

-0.14

chw

-0.14

lag

-0.14

POSITIVE LOGITS

ãĥ³ãĥĸ

0.16

agma

0.16

ëĪĦ

0.16

nee

0.15

ãĤ·ãĥ§ãĥ³

0.14

 Hizmet

0.14

 sobÄĽ

0.14

otics

0.14

eÄį

0.14

Activations Density 0.004%

instances of characters or representations in various narratives

No Comments

No Known Activations