INDEX

Explanations

names of individuals and their affiliations or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

EMU

-0.17

crest

-0.16

 EXIT

-0.15

inki

-0.15

ÅĻiv

-0.14

inand

-0.14

unta

-0.14

.scalablytyped

-0.14

atorial

-0.14

ibles

-0.14

POSITIVE LOGITS

eger

0.15

 probation

0.15

 Rowe

0.15

lude

0.15

 prob

0.14

abra

0.14

elt

0.14

haps

0.14

 Prob

0.14

Activations Density 0.031%

names of individuals and their affiliations or roles

No Comments

No Known Activations