INDEX

Explanations

references to the term "Wolf" in various contexts and variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

agger

-0.16

eous

-0.15

vÃ¡

-0.15

umerator

-0.15

NodeType

-0.15

ë°

-0.15

olland

-0.14

ÑĸÑģ

-0.14

á»ĳc

-0.14

ajs

-0.14

POSITIVE LOGITS

pack

0.30

owitz

0.27

enden

0.25

hound

0.25

enstein

0.24

enso

0.24

sonian

0.23

endale

0.23

gram

0.22

Activations Density 0.010%

references to the term "Wolf" in various contexts and variations

No Comments

No Known Activations