INDEX

Explanations

mentions of "tape" in various contexts

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

rie

-0.16

ASP

-0.15

Ø´Øª

-0.15

Å¡t

-0.14

eman

-0.14

imar

-0.14

nea

-0.14

ÑģÐµÐ½

-0.14

quine

-0.14

 Cutter

-0.14

POSITIVE LOGITS

diag

0.15

krom

0.15

ichern

0.15

icorn

0.15

-flat

0.15

oplevel

0.14

 motto

0.14

á»©a

0.14

ilarity

0.14

=Value

0.14

Activations Density 0.005%

mentions of "tape" in various contexts

No Comments

No Known Activations