INDEX

Explanations

programming-related keywords or syntax

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

 Flags

-0.17

Flags

-0.16

 flags

-0.16

EAR

-0.16

flags

-0.15

 FLAGS

-0.15

_FLAGS

-0.15

 flood

-0.15

ear

-0.14

isl

-0.14

POSITIVE LOGITS

pis

0.16

ãĥªãĥ¼ãĤº

0.16

tery

0.16

ycler

0.15

lama

0.15

gz

0.14

Î¿ÏħÏĤ

0.14

 pÅĻÃŃ

0.14

kers

0.14

Mal

0.14

Activations Density 0.001%

programming-related keywords or syntax

No Comments

No Known Activations