INDEX

Explanations

references to months and specific dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ersions

-0.16

Batch

-0.15

 Batch

-0.15

_mD

-0.15

etsk

-0.15

-fontawesome

-0.15

assage

-0.14

_mE

-0.14

.Inner

-0.14

irket

-0.14

POSITIVE LOGITS

 quit

0.15

ÎµÏį

0.15

 chez

0.14

ium

0.14

itr

0.13

us

0.13

opus

0.13

 routed

0.13

incy

0.13

uen

0.13

Activations Density 0.061%

references to months and specific dates

No Comments

No Known Activations