INDEX

Explanations

references to locations and associated images in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ough

-0.16

-↵

-0.15

ummer

-0.15

ipes

-0.15

 intros

-0.15

ent

-0.15

Sp

-0.14

ÛĮØ³Øª

-0.14

 Hutchinson

-0.14

POSITIVE LOGITS

ukan

0.17

RAIN

0.17

aney

0.16

ileges

0.16

MimeType

0.16

PFN

0.16

abr

0.15

éľ²

0.15

ityEngine

0.15

Å¡e

0.15

Activations Density 0.008%

references to locations and associated images in news articles

No Comments

No Known Activations