INDEX

Explanations

programming-related language structures and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rush

-0.17

ults

-0.15

_representation

-0.15

enes

-0.15

 treatment

-0.14

 franchise

-0.14

rog

-0.14

ingly

-0.14

OPS

-0.14

éĻĲ

-0.14

POSITIVE LOGITS

/popper

0.17

.makeText

0.16

axter

0.16

uzz

0.15

usat

0.15

-controls

0.15

icago

0.15

hlen

0.14

ussy

0.14

isman

0.13

Activations Density 0.003%

programming-related language structures and documentation

No Comments

No Known Activations