INDEX

Explanations

references to academic citations or sources in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ngrx

-0.16

uras

-0.15

DEX

-0.15

lap

-0.15

urus

-0.15

duit

-0.15

 BindingFlags

-0.15

urette

-0.15

TK

-0.14

urally

-0.14

POSITIVE LOGITS

ÑĤÐ¾ÑĢ

0.14

lund

0.14

 elig

0.13

iset

0.13

åŁŁ

0.13

0.12

Activations Density 0.015%

references to academic citations or sources in a research context

No Comments

No Known Activations