INDEX

Explanations

key concepts related to interactions and relationships in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ople

-0.16

emmel

-0.14

osit

-0.13

Ð½ÑıÑĤÐ¸

-0.13

uries

-0.13

imson

-0.13

.opendaylight

-0.13

_vocab

-0.13

elman

-0.13

 cylindrical

-0.13

POSITIVE LOGITS

è³¢

0.17

wi

0.16

rag

0.15

attles

0.14

sher

0.14

bucks

0.14

 Leslie

0.14

.spatial

0.14

dehy

0.14

 interiors

0.14

Activations Density 0.100%

key concepts related to interactions and relationships in various contexts

No Comments

No Known Activations