INDEX

Explanations

proper nouns related to locations and landmarks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģ®æĸ¹

-0.16

itsu

-0.15

gest

-0.15

ibre

-0.15

ierre

-0.15

±

-0.14

spor

-0.14

nu

-0.14

 subs

-0.14

eter

-0.14

POSITIVE LOGITS

quier

0.15

Occurrences

0.14

eyJ

0.14

eson

0.14

cox

0.13

_SOFT

0.13

MOM

0.13

SEG

0.13

_CNTL

0.13

.wik

0.13

Activations Density 0.662%

proper nouns related to locations and landmarks

No Comments

No Known Activations