INDEX

Explanations

geographic locations and directional references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ens

-0.18

¤

-0.17

plex

-0.16

ense

-0.16

-0.15

 Isles

-0.15

iske

-0.15

enser

-0.14

isku

-0.14

yth

-0.14

POSITIVE LOGITS

opis

0.16

licas

0.15

æĭ³

0.15

oreach

0.14

PK

0.14

_accessor

0.14

qui

0.14

_blocking

0.13

stal

0.13

hya

0.13

Activations Density 0.027%

geographic locations and directional references

No Comments

No Known Activations