INDEX

Explanations

interactions and relationships among characters or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

yre

-0.15

chalk

-0.14

 myself

-0.14

ä»ĺãģĳ

-0.14

/backend

-0.14

Ã¦re

-0.14

ÙĬÙĩ

-0.14

ichten

-0.14

olas

-0.14

(--

-0.14

POSITIVE LOGITS

 themselves

0.16

zem

0.15

-helper

0.15

/left

0.14

èµı

0.14

PHA

0.14

poon

0.14

fig

0.14

nr

0.13

Sok

0.13

Activations Density 0.299%

interactions and relationships among characters or groups

No Comments

No Known Activations