INDEX

Explanations

references to the organization or term "G" 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

etta

-0.17

ãģĹãĤĩãģĨ

-0.17

ui

-0.17

oda

-0.16

-UA

-0.15

Ã¼n

-0.14

ibir

-0.14

.xz

-0.14

uo

-0.14

ê´

-0.14

POSITIVE LOGITS

win

0.20

ator

0.19

ators

0.19

nage

0.18

raft

0.18

ander

0.17

annon

0.17

rier

0.17

omers

0.16

omer

0.16

Activations Density 0.031%

references to the organization or term "G" in various contexts

No Comments

No Known Activations