INDEX

Explanations

expressions of confusion or dismay

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Fog

-0.16

-0.15

panse

-0.15

atrix

-0.15

ule

-0.14

uen

-0.14

TRACE

-0.14

 Fitzgerald

-0.14

 (*((

-0.13

 ÐŀÐ´Ð½Ð°

-0.13

POSITIVE LOGITS

ongan

0.17

ndon

0.15

ASURE

0.15

 èĲ

0.15

lund

0.14

nud

0.14

(exports

0.14

ilden

0.14

à¤ł

0.14

lap

0.14

Activations Density 0.067%

expressions of confusion or dismay

No Comments

No Known Activations