INDEX

Explanations

references to walls or barriers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oq

-0.16

trap

-0.15

.clientHeight

-0.15

 traps

-0.14

ÑĢÑĮ

-0.14

ÙħØ§ÙĦ

-0.14

linger

-0.14

Gas

-0.14

 Emotional

-0.14

agan

-0.14

POSITIVE LOGITS

TECTED

0.17

ployment

0.16

orsch

0.15

rastructure

0.14

opi

0.14

privileged

0.14

STALL

0.14

íį¼

0.14

Ã¶r

0.14

uja

0.14

Activations Density 0.003%

references to walls or barriers

No Comments

No Known Activations