INDEX

Explanations

references to movies, particularly those with comedic or fantastical elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

olit

-0.18

_simps

-0.15

STAT

-0.14

enson

-0.14

erre

-0.14

è¾ħ

-0.14

cela

-0.14

ieÅ¼

-0.13

êµ´

-0.13

unday

-0.13

POSITIVE LOGITS

nak

0.14

 Feature

0.14

 Priv

0.14

 Guerr

0.14

lex

0.13

ocities

0.13

 feature

0.13

 Amazon

0.13

 Rank

0.13

Activations Density 0.028%

references to movies, particularly those with comedic or fantastical elements

No Comments

No Known Activations