INDEX

Explanations

references to data attributes in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.scalablytyped

-0.21

ãĥ¼ãĥĹ

-0.18

itÃ¤

-0.17

Descriptors

-0.16

æŀ¶

-0.15

ustr

-0.15

aylight

-0.15

PILE

-0.15

aney

-0.15

å¾½

-0.15

POSITIVE LOGITS

´Ī

0.17

Dismiss

0.15

 role

0.15

stal

0.15

dismiss

0.15

ubby

0.14

Orig

0.13

 calf

0.13

Activations Density 0.027%

references to data attributes in a coding context

No Comments

No Known Activations