INDEX

Explanations

references to the term "valley" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

elli

-0.17

iddi

-0.16

nost

-0.16

zell

-0.15

éļľ

-0.15

nosti

-0.14

aviors

-0.14

qual

-0.14

yÄ±

-0.14

iu

-0.14

POSITIVE LOGITS

-wide

0.20

wide

0.18

 Forge

0.17

ence

0.16

enda

0.16

-val

0.15

ued

0.15

entin

0.15

-span

0.15

side

0.14

Activations Density 0.016%

references to the term "valley" and its variations in context

No Comments

No Known Activations